@inproceedings{0e88fc09389842a4befe902460ca6d3f,
title = "Distributed privacy-preserving record linkage using pivot-based filter techniques",
abstract = "Privacy-preserving record linkage (PPRL) aims at linking person-related records from different data sources while protecting privacy. It is applied in medical research to link health data without revealing sensible person-related data. We propose and evaluate a new parallel PPRL approach based on Apache Flink that aims at high performance and scalability to large datasets. The approach supports a pivot-based filtering method for metric distance functions that saves many similarity computations. We describe our distributed approaches to determine pivots and pivot-based linkage. We also demonstrate the high efficiency of the approach for different datasets and configurations.",
keywords = "PPRL",
author = "Marcel Gladbach and Ziad Sehili and Thomas Kudra{\ss} and Peter Christen and Erhard Rahm",
note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 34th IEEE International Conference on Data Engineering Workshops, ICDEW 2018 ; Conference date: 16-04-2018 Through 19-04-2018",
year = "2018",
month = jul,
day = "2",
doi = "10.1109/ICDEW.2018.00013",
language = "English",
series = "Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "33--38",
booktitle = "Proceedings - IEEE 34th International Conference on Data Engineering Workshops, ICDEW 2018",
address = "United States",
}